First Push

README.md

@@ -0,0 +1,29 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Find your model_id: jucamohedano/ppo-SnowballTargetTESTCOLAB
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eead29ad8bb212a2113c1637bf1bd253c5758678e06a97ee01c355fce0f5726
+size 646532

SnowballTarget/SnowballTarget-1599800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556336da5b97998b9c25eaf0ede21c3a9888cedde0e9427f3e6c4278adb5232e
+size 646532

SnowballTarget/SnowballTarget-1599800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d022ce816909a772c1ced94480e2966d642fa41433fa9c44ce214736f47306
+size 3843968

SnowballTarget/SnowballTarget-1649800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1e670247c62ff12ae86eac7825d43a8dee2a3ef56b7e35f48cea7b3256e060
+size 646532

SnowballTarget/SnowballTarget-1649800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324160db518c65fae283d1c2d5070bb3a10cdcfafda5d15524a8933c5b004da9
+size 3843968

SnowballTarget/SnowballTarget-1699800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6760a0747946292b15e4e433baba45d964f4d95b66ad6d4c475bd54046a07dc0
+size 646532

SnowballTarget/SnowballTarget-1699800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd6c581ba0b5fca4c6553c91056c7a1f401745eb41d54ef13c4cf1582813fba
+size 3843968

SnowballTarget/SnowballTarget-1749800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c1713ce7d983679e3bfb0b7fa8b33f5fcb0047f17be9e76e6f4082076afc9a
+size 646532

SnowballTarget/SnowballTarget-1749800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d3be8846ca51f8e740615dd7df2e42a6a11b3185757ca58360a2fe7481371a
+size 3843968

SnowballTarget/SnowballTarget-1799800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd5ae0d80c790b5a9a7863db76e0e59a7d78f2d616eb70c9a9fa8bbe66c98a6
+size 646532

SnowballTarget/SnowballTarget-1799800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4a6fc11c653d9e82509fcc24bfeb7fce49813b6c1f5f92f02b27bbbdb5e919
+size 3843968

SnowballTarget/SnowballTarget-1849800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbf42ffb263c4eefe5c83f5549f2c8175bb9bd632cca76ecdf88b522241510a
+size 646532

SnowballTarget/SnowballTarget-1849800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99ee044a87b8e74517fd16658211c67b69b89599d856f9ee23a428cbfae6364
+size 3843968

SnowballTarget/SnowballTarget-1899800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3841f3bddee6575d46acb51a4748545fea2934d8e59638b1ecca5c6b5534cef5
+size 646532

SnowballTarget/SnowballTarget-1899800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b621c3069b197ebffe39e2a15e2b46ff27da071ca23e18b4d90c4f82dd3768
+size 3843968

SnowballTarget/SnowballTarget-1949800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7304b9a954b7e6c7cfc11093c56c7608948f5f0d2791f24043ca4a0fec1b51
+size 646532

SnowballTarget/SnowballTarget-1949800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451fdc5ef2f15050b70a8eb9171960a81f005f4f3345fa30921221eb12351941
+size 3843968

SnowballTarget/SnowballTarget-1999800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eead29ad8bb212a2113c1637bf1bd253c5758678e06a97ee01c355fce0f5726
+size 646532

SnowballTarget/SnowballTarget-1999800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a45bc3f9b82095ec1384afb08acb8a23eb994e3c42a47f6e85720fa050800e
+size 3843968

SnowballTarget/SnowballTarget-2002000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eead29ad8bb212a2113c1637bf1bd253c5758678e06a97ee01c355fce0f5726
+size 646532

SnowballTarget/SnowballTarget-2002000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951f5efb7012440a814d5d734178dde00b2d135325fb7cf835006fddbd9e33fb
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951f5efb7012440a814d5d734178dde00b2d135325fb7cf835006fddbd9e33fb
+size 3843968

SnowballTarget/events.out.tfevents.1685388051.dc212886b4fe.52879.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2255794ef7422cfe545ea0736c1b54fbb5e333168883b8fdc7d1155df4afe3b3
+size 170541

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 640, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 256, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,77 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 640
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 256
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.142 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.817643 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 1 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 53695 frames, [16.0 KB-32.0 KB]: 910 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 238 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 41
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11387 frames, [8.0 MB-16.0 MB]: 29512 frames, [16.0 MB-32.0 MB]: 13707 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 54606 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 53060 frames, [64.0 KB-128.0 KB]: 1546 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54606 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 39.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54606 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 0.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54605 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 54606 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 54606 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.502884030342102,
+            "min": 0.4950654208660126,
+            "max": 2.8556060791015625,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 5498.53369140625,
+            "min": 4383.80419921875,
+            "max": 31537.314453125,
+            "count": 200
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 200
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 200
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 1999800.0,
+            "min": 9800.0,
+            "max": 1999800.0,
+            "count": 200
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 1999800.0,
+            "min": 9800.0,
+            "max": 1999800.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.40530014038086,
+            "min": 0.5898134112358093,
+            "max": 14.528471946716309,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 720.2650146484375,
+            "min": 28.900856018066406,
+            "max": 726.423583984375,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 28.14,
+            "min": 2.979591836734694,
+            "max": 28.82,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1407.0,
+            "min": 146.0,
+            "max": 1441.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 28.14,
+            "min": 2.979591836734694,
+            "max": 28.82,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1407.0,
+            "min": 146.0,
+            "max": 1441.0,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07086786612064815,
+            "min": 0.058216861729469035,
+            "max": 0.07708449171332175,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.35433933060324074,
+            "min": 0.23554468888780283,
+            "max": 0.48754120100033926,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15724290083436404,
+            "min": 0.12282182563607599,
+            "max": 0.31365526908752966,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7862145041718203,
+            "min": 0.5551439361537205,
+            "max": 1.5746072739995773,
+            "count": 200
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 6.900997699999907e-07,
+            "min": 6.900997699999907e-07,
+            "max": 0.00029925000025000004,
+            "count": 200
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.4504988499999535e-06,
+            "min": 3.4504988499999535e-06,
+            "max": 0.0018529200823599998,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10023000000000001,
+            "min": 0.10023000000000001,
+            "max": 0.19974999999999998,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5011500000000001,
+            "min": 0.4051,
+            "max": 1.3176400000000004,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 2.1476999999999845e-05,
+            "min": 2.1476999999999845e-05,
+            "max": 0.004987525,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00010738499999999923,
+            "min": 0.00010738499999999923,
+            "max": 0.030890235999999998,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1685388050",
+        "python_version": "3.10.11 (main, Apr  5 2023, 14:15:10) [GCC 9.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --force --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1685392206"
+    },
+    "total": 4156.039179292,
+    "count": 1,
+    "self": 0.7836949049979012,
+    "children": {
+        "run_training.setup": {
+            "total": 0.041554798001016025,
+            "count": 1,
+            "self": 0.041554798001016025
+        },
+        "TrainerController.start_learning": {
+            "total": 4155.213929589001,
+            "count": 1,
+            "self": 5.278144760817668,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.004054107999764,
+                    "count": 1,
+                    "self": 5.004054107999764
+                },
+                "TrainerController.advance": {
+                    "total": 4144.725738117182,
+                    "count": 182017,
+                    "self": 2.429764486472777,
+                    "children": {
+                        "env_step": {
+                            "total": 4142.295973630709,
+                            "count": 182017,
+                            "self": 2775.3954018626846,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1364.4222511536864,
+                                    "count": 182017,
+                                    "self": 16.330676386962296,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1348.091574766724,
+                                            "count": 182017,
+                                            "self": 1348.091574766724
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.4783206143383723,
+                                    "count": 182017,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4142.147350692056,
+                                            "count": 182017,
+                                            "is_parallel": true,
+                                            "self": 1842.874680491137,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0026682219995564083,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006816909972258145,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0019865310023305938,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0019865310023305938
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.033951434001210146,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005661830000462942,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003298410010756925,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003298410010756925
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03106628200112027,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03106628200112027
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001989127998967888,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00036292299955675844,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016262049994111294,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016262049994111294
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2299.2726702009186,
+                                                    "count": 182016,
+                                                    "is_parallel": true,
+                                                    "self": 90.86473994406515,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 50.26805471483385,
+                                                            "count": 182016,
+                                                            "is_parallel": true,
+                                                            "self": 50.26805471483385
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1845.497618679061,
+                                                            "count": 182016,
+                                                            "is_parallel": true,
+                                                            "self": 1845.497618679061
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 312.6422568629587,
+                                                            "count": 182016,
+                                                            "is_parallel": true,
+                                                            "self": 58.7462448367296,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 253.89601202622907,
+                                                                    "count": 1820160,
+                                                                    "is_parallel": true,
+                                                                    "self": 253.89601202622907
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.001476541001466103,
+                    "count": 1,
+                    "self": 0.001476541001466103,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 4127.841178099707,
+                                    "count": 2399333,
+                                    "is_parallel": true,
+                                    "self": 54.82031182758692,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1411.787706635072,
+                                            "count": 2399333,
+                                            "is_parallel": true,
+                                            "self": 1403.902087201066,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 7.885619434006003,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 7.885619434006003
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 2661.2331596370477,
+                                            "count": 964,
+                                            "is_parallel": true,
+                                            "self": 769.5147323549772,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1891.7184272820705,
+                                                    "count": 46191,
+                                                    "is_parallel": true,
+                                                    "self": 1891.7184272820705
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2045160620000388,
+                    "count": 1,
+                    "self": 0.001140428998041898,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2033756330019969,
+                            "count": 1,
+                            "self": 0.2033756330019969
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 1599800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599800.onnx",
+                "reward": 25.5,
+                "creation_time": 1685391386.9660883,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599800.pt"
+                ]
+            },
+            {
+                "steps": 1649800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649800.onnx",
+                "reward": 27.7,
+                "creation_time": 1685391485.9490118,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649800.pt"
+                ]
+            },
+            {
+                "steps": 1699800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699800.onnx",
+                "reward": 28.857142857142858,
+                "creation_time": 1685391589.1279216,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699800.pt"
+                ]
+            },
+            {
+                "steps": 1749800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749800.onnx",
+                "reward": 30.25,
+                "creation_time": 1685391692.3272617,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749800.pt"
+                ]
+            },
+            {
+                "steps": 1799800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799800.onnx",
+                "reward": 29.0,
+                "creation_time": 1685391794.810225,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799800.pt"
+                ]
+            },
+            {
+                "steps": 1849800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849800.onnx",
+                "reward": 27.22222222222222,
+                "creation_time": 1685391893.611376,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849800.pt"
+                ]
+            },
+            {
+                "steps": 1899800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899800.onnx",
+                "reward": 27.166666666666668,
+                "creation_time": 1685391995.701991,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899800.pt"
+                ]
+            },
+            {
+                "steps": 1949800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949800.onnx",
+                "reward": 28.666666666666668,
+                "creation_time": 1685392098.3499272,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949800.pt"
+                ]
+            },
+            {
+                "steps": 1999800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999800.onnx",
+                "reward": null,
+                "creation_time": 1685392204.9560597,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999800.pt"
+                ]
+            },
+            {
+                "steps": 2002000,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2002000.onnx",
+                "reward": 27.818181818181817,
+                "creation_time": 1685392205.4866705,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2002000.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2002000,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.818181818181817,
+            "creation_time": 1685392205.4866705,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2002000.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}